Bayesian mechanics for stationary processes
File(s)rspa.2021.0518.pdf (1.97 MB)
Published version
Author(s)
Da Costa, Lancelot
Friston, Karl
Heins, Conor
Pavliotis, Grigorios A
Type
Journal Article
Abstract
This paper develops a Bayesian mechanics for adaptive systems. Firstly, we model the interface between a system and its environment with a Markov blanket. This affords conditions under which states internal to the blanket encode information about external states. Second, we introduce dynamics and represent adaptive systems as Markov blankets at steady state. This allows us to identify a wide class of systems whose internal states appear to infer external states, consistent with variational inference in Bayesian statistics and theoretical neuroscience. Finally, we partition the blanket into sensory and active states. It follows that active states can be seen as performing active inference and well-known forms of stochastic control (such as PID control), which are prominent formulations of adaptive behaviour in theoretical biology and engineering.
Date Issued
2021-12-22
Date Acceptance
2021-10-27
Citation
Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2021, 477 (2256), pp.1-26
ISSN
1364-5021
Publisher
The Royal Society
Start Page
1
End Page
26
Journal / Book Title
Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
Volume
477
Issue
2256
Copyright Statement
© 2021 The Authors.
Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited.
Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited.
Sponsor
Engineering & Physical Science Research Council (EPSRC)
Le Fonds National de la Recherche
Identifier
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000727797600004&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
Grant Number
EP/P031587/1
13568875
Subjects
Science & Technology
Multidisciplinary Sciences
Science & Technology - Other Topics
Markov blanket
variational Bayesian inference
active inference
non-equilibrium steady state
predictive processing
free-energy principle
FREE-ENERGY PRINCIPLE
ENTROPY PRODUCTION
INFERENCE
BRAIN
MODEL
Publication Status
Published
Article Number
ARTN 20210518
Date Publish Online
2021-12-08